COX: Exposing CUDA warp-level functions to CPUs

R Han, J Lee, J Sim, H Kim - ACM Transactions on Architecture and …, 2022 - dl.acm.org
As CUDA becomes the de facto programming language among data parallel applications
such as high-performance computing or machine learning applications, running CUDA on …

The METASAT Model-Based Engineering Workflow and Digital Twin Concept

AJ Calderón, I Yarza, S Sinisi, L Lazzara… - … , Automation & Test …, 2024 - ieeexplore.ieee.org
Considering the complexity in the design of future satellites and the need for compliance
with ECSS standards, the METASAT project proposes a novel design methodology based …

COX: CUDA on X86 by Exposing Warp-Level Functions to CPUs

R Han, J Lee, J Sim, H Kim - arXiv preprint arXiv:2112.10034, 2021 - arxiv.org
As CUDA programs become the de facto program among data parallel applications such as
high-performance computing or machine learning applications, running CUDA on other …

The METASAT Modelling and Code Generation Toolchain for XtratuM and Hardware Accelerators

AJ Calderón, A Amonarriz, M Hernández… - 2024 27th Euromicro …, 2024 - ieeexplore.ieee.org
Given the complex design requirements of future satellites and the need to comply with
ECSS standards, the METASAT project introduces an innovative design approach that uses …

Programming Model Extensions for General-Purpose Processing-In-Memory

H Hong, L Sommer, B Kim, M Kashkarov… - ISC High …, 2024 - ieeexplore.ieee.org
The performance of many applications is limited by the available memory bandwidth. One
approach to improve the performance of such memory-bound applications is to move the …

Performance monitoring of real-time applications in RISC-V platforms

NFP Soares - 2024 - recipp.ipp.pt
Real-time systems are an important field of research, specially when considering that these
systems interact with the real-world and their tasks have direct impact in human lives and …

GPU Wavefront Splitting for Safety-Critical Systems

A Klashtorny - 2022 - uwspace.uwaterloo.ca
Graphics processing units (GPUs) are compute platforms that are ideal for highly parallel
workloads due to their high degree of hardware parallelism. Parallelism offered by GPUs …